AutoStatLib 0.2.21__tar.gz → 0.2.23__tar.gz

autostatlib-0.2.23/PKG-INFO

@@ -0,0 +1,192 @@
+Metadata-Version: 2.4
+Name: AutoStatLib
+Version: 0.2.23
+Summary: AutoStatLib - a simple statistical analysis tool
+Author: Stemonitis, SciWare LLC
+Author-email: konung-yaropolk <yaropolk1995@gmail.com>
+License-Expression: LGPL-2.1-or-later
+Project-URL: Homepage, https://github.com/konung-yaropolk/AutoStatLib
+Project-URL: Repository, https://github.com/konung-yaropolk/AutoStatLib.git
+Project-URL: Issues, https://github.com/konung-yaropolk/AutoStatLib/issues
+Keywords: Science,Statistics
+Classifier: Programming Language :: Python
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Operating System :: OS Independent
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: Intended Audience :: Science/Research
+Classifier: Natural Language :: English
+Classifier: Topic :: Software Development :: Libraries
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Classifier: Topic :: Scientific/Engineering
+Classifier: Topic :: Scientific/Engineering :: Information Analysis
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: numpy
+Requires-Dist: scipy
+Requires-Dist: statsmodels
+Requires-Dist: matplotlib
+Requires-Dist: seaborn
+Requires-Dist: scikit-posthocs
+Requires-Dist: pandas
+Dynamic: license-file
+
+# AutoStatLib - python library for automated statistical analysis
+
+[![pypi_version](https://img.shields.io/pypi/v/AutoStatLib?label=PyPI&color=green)](https://pypi.org/project/AutoStatLib)
+[![GitHub Release](https://img.shields.io/github/v/release/konung-yaropolk/AutoStatLib?label=GitHub&color=green&link=https%3A%2F%2Fgithub.com%2Fkonung-yaropolk%2FAutoStatLib)](https://github.com/konung-yaropolk/AutoStatLib)
+[![PyPI - License](https://img.shields.io/pypi/l/AutoStatLib)](https://pypi.org/project/AutoStatLib)
+[![Python](https://img.shields.io/badge/Python-v3.10%5E-green?logo=python)](https://pypi.org/project/AutoStatLib)
+[![PyPI - Downloads](https://img.shields.io/pypi/dm/AutoStatLib?label=PyPI%20stats&color=blue)](https://pypi.org/project/AutoStatLib)
+
+### To install run the command:
+
+```bash
+pip install autostatlib
+```
+
+### Example use case:
+
+See the /demo directory on Git repo or
+use the following example:
+
+```python
+import numpy as np
+import AutoStatLib
+
+# generate random data:
+groups = 2
+n = 30
+
+# normal data
+data_norm = [list(np.random.normal(.5*i + 4, abs(1-.2*i), n))
+        for i in range(groups)]
+
+# non-normal data
+data_uniform = [list(np.random.uniform(i+3, i+1, n)) for i in range(groups)]
+
+
+# set the parameters:
+paired = False     # is groups dependent or not
+tails = 2          # two-tailed or one-tailed result
+popmean = 0        # population mean - only for single-sample tests needed
+
+# initiate the analysis
+analysis = AutoStatLib.StatisticalAnalysis(
+    data_norm, paired=paired, tails=tails, popmean=popmean)
+```
+
+now you can preform automated statistical test selection:
+
+```python
+analysis.RunAuto()
+```
+
+or you can choose specific tests:
+
+```python
+# 2 groups independent:
+analysis.RunTtest()
+analysis.RunMannWhitney()
+
+# 2 groups paired"
+analysis.RunTtestPaired()
+analysis.RunWilcoxon()
+
+# 3 and more independed groups comparison:
+analysis.RunOnewayAnova()
+analysis.RunKruskalWallis()
+
+# 3 and more depended groups comparison:
+analysis.RunOnewayAnovaRM()
+analysis.RunFriedman()
+
+# single group tests"
+analysis.RunTtestSingleSample()
+analysis.RunWilcoxonSingleSample()
+```
+
+Test summary will be printed to the console.
+You can also get it as a python string via *GetSummary()* method.
+
+---
+
+Test results are accessible as a dictionary via *GetResult()* method:
+
+```python
+results = analysis.GetResult()
+```
+
+The results dictionary keys with representing value types:
+
+```
+{
+    'p_value' :                    String
+    'Significance(p<0.05)' :       Boolean
+    'Stars_Printed' :              String
+    'Test_Name' :                  String
+    'Groups_Compared' :            Integer
+    'Population_Mean' :            Float   (taken from the input)
+    'Data_Normaly_Distributed' :   Boolean
+    'Parametric_Test_Applied' :    Boolean
+    'Paired_Test_Applied' :        Boolean
+    'Tails' :                      Integer (taken from the input)
+    'p_value_exact' :              Float
+    'Stars' :                      Integer
+    'Warnings' :                   String
+    'Groups_N' :                   List of integers
+    'Groups_Median' :              List of floats
+    'Groups_Mean' :                List of floats
+    'Groups_SD' :                  List of floats
+    'Groups_SE' :                  List of floats
+    'Samples' :                    List of input values by groups
+                                           (taken from the input)
+    'Posthoc_Matrix' :             2D List of floats
+    'Posthoc_Matrix_bool' :        2D List of Boolean
+    'Posthoc_Matrix_printed':      2D List of String
+    'Posthoc_Matrix_stars':        2D List of String
+}
+```
+
+If errors occured, *GetResult()* returns an empty dictionary
+
+---
+
+## Alpha dev status.
+
+### TODO:
+
+-- Anova: posthocs  
+-- Anova: add 2-way anova and 3-way anova  
+-- onevay Anova: add repeated measures (for normal dependent values) with and without Gaisser-Greenhouse correction  
+-- onevay Anova: add Brown-Forsithe and Welch (for normal independent values with unequal SDs between groups)  
+-- paired T-test: add ratio-paired t-test (ratios of paired values are consistent)  
+-- add Welch test (for norm data unequal variances)  
+-- add Kolmogorov-smirnov test (unpaired nonparametric 2 sample, compare cumulative distributions)  
+-- add independent t-test with Welch correction (do not assume equal SDs in groups)  
+-- add correlation test, correlation diagram  
+-- add linear regression, regression diagram  
+-- add QQ plot  
+-- n-sample tests: add onetail option  
+
+✅ done -- detailed normality test results  
+✅ done -- added posthoc: Kruskal-Wallis Dunn's multiple comparisons  
+
+tests check:  
+1-sample:  
+✅ok --Wilcoxon 2,1 tails  
+✅ok --t-tests 2,1 tails  
+
+2-sample:  
+✅ok --Wilcoxon 2,1 tails  
+✅ok --Mann-whitney 2,1 tails  
+✅ok --t-tests 2,1 tails  
+
+n-sample:  
+✅ok --Kruskal-Wallis 2 tail  
+✅ok --Dunn's multiple comparisons  
+✅ok --Friedman 2 tail  
+✅ok --one-way ANOVA 2-tailed  
+✅ok --Tukey`s multiple comparisons  

{autostatlib-0.2.21 → autostatlib-0.2.23}/pyproject.toml

@@ -5,7 +5,8 @@ build-backend = "setuptools.build_meta"
 [project]
 name = "AutoStatLib"
 dynamic = ["version", "dependencies"]
-license = {file = "LICENSE"}
+license = "LGPL-2.1-or-later"
+# license = {file = "LICENSE"}
 authors = [
   { name="konung-yaropolk", email="yaropolk1995@gmail.com" },
   { name="Stemonitis"},
@@ -18,8 +19,8 @@ requires-python = ">=3.10"
 classifiers = [
     "Programming Language :: Python",
     "Programming Language :: Python :: 3",
-    "Programming Language :: Python :: 3.12",
-    "License :: OSI Approved :: GNU Lesser General Public License v2 or later (LGPLv2+)",
+    "Programming Language :: Python :: 3.10",
+    # "License :: OSI Approved :: GNU Lesser General Public License v2 or later (LGPLv2+)",
     "Operating System :: OS Independent",
     "Development Status :: 4 - Beta",
     "Intended Audience :: Developers",

{autostatlib-0.2.21 → autostatlib-0.2.23}/src/AutoStatLib/AutoStatLib.py

@@ -19,7 +19,9 @@ class StatisticalAnalysis(StatisticalTests, NormalityTests, TextFormatting, Help
                  popmean=None,
                  posthoc=False,
                  verbose=True,
-                 groups_name=[]):
+                 raise_errors=False,
+                 groups_name=[],
+                 subgrouping=[]):
         self.results = None
         self.error = False
         self.groups_list = groups_list
@@ -28,10 +30,11 @@ class StatisticalAnalysis(StatisticalTests, NormalityTests, TextFormatting, Help
         self.popmean = popmean
         self.posthoc = posthoc
         self.verbose = verbose
+        self.raise_errors = raise_errors
         self.n_groups = len(self.groups_list)
         self.groups_name = [groups_name[i % len(groups_name)]
-                             for i in range(self.n_groups)] if groups_name and groups_name != [''] else [f'Group {i+1}' for i in range(self.n_groups)]
-
+                            for i in range(self.n_groups)] if groups_name and groups_name != [''] else [f'Group {i+1}' for i in range(self.n_groups)]
+        self.subgrouping = subgrouping if subgrouping else [0]
         self.warning_flag_non_numeric_data = False
         self.summary = 'AutoStatLib v{}'.format(__version__)
 
@@ -99,7 +102,6 @@ class StatisticalAnalysis(StatisticalTests, NormalityTests, TextFormatting, Help
             'no_pop_mean_set':                 '\nWarning: No Population Mean was set up for single-sample test, used default 0 value.\n         The results might be skewed. \n         Please, set the Population Mean and run the test again.\n',
         }
 
-
     def run_test(self, test='auto'):
 
         # reset values from previous tests
@@ -111,6 +113,7 @@ class StatisticalAnalysis(StatisticalTests, NormalityTests, TextFormatting, Help
         self.test_id = None
         self.test_stat = None
         self.p_value = None
+        self.parametric = None
         self.posthoc_matrix_df = None
         self.posthoc_matrix = []
         self.posthoc_name = ''
@@ -128,7 +131,7 @@ class StatisticalAnalysis(StatisticalTests, NormalityTests, TextFormatting, Help
         # delete the empty cols from input
         self.data = [col for col in self.data if any(
             x is not None for x in col)]
-        
+
         # User input assertion block
         try:
             assert self.data, 'There is no input data'
@@ -137,9 +140,9 @@ class StatisticalAnalysis(StatisticalTests, NormalityTests, TextFormatting, Help
             assert all(len(
                 group) >= 4 for group in self.data), 'Each group must contain at least four values'
             assert not (self.paired is True
-                        and not all(len(lst) == len(self.data[0]) for lst in self.data)), 'Paired groups must have the same length'
+                        and not all(len(lst) == len(self.data[0]) for lst in self.data)), 'Paired samples must have the same length'
             assert not (test in self.test_ids_dependent
-                        and not all(len(lst) == len(self.data[0]) for lst in self.data)), 'Groups must have the same length for dependent groups test'
+                        and not all(len(lst) == len(self.data[0]) for lst in self.data)), 'Samples must have the same length for the dependend statistics test'
             assert not (test in self.test_ids_2sample
                         and self.n_groups != 2), f'Only two groups of data must be given for 2-groups tests, got {self.n_groups}'
             assert not (test in self.test_ids_1sample
@@ -147,11 +150,22 @@ class StatisticalAnalysis(StatisticalTests, NormalityTests, TextFormatting, Help
             assert not (test in self.test_ids_3sample
                         and self.n_groups < 3), f'At least three groups of data must be given for multi-groups tests, got {self.n_groups}'
         except AssertionError as error:
-            self.log('\nTest  :', test)
-            self.log('Error :', error)
-            self.log('-'*67 + '\n')
-            self.error = True
-            print(self.summary)
+            self.run_test_by_id('none')
+            self.results = self.create_results_dict()
+
+            if self.raise_errors:
+                raise ValueError(error)
+
+            # Print errmessage:
+            if self.verbose:
+                self.log('\nTest  :', test)
+                self.log('Error :', error)
+                self.log('-'*67 + '\n')
+                self.error = True
+                print(self.summary)
+            else:
+                print('AutoStatLib Error :', error)
+
             return
 
         # Print the data
@@ -165,7 +179,7 @@ class StatisticalAnalysis(StatisticalTests, NormalityTests, TextFormatting, Help
         self.log('Shapiro-Wilk, Lilliefors, Anderson-Darling, D\'Agostino-Pearson')
         self.log(
             '[+] -positive, [-] -negative, [ ] -too small group for the test\n')
-        self.log('        Test   :   SW  LF  AD  AP  ')
+        self.log('                   SW  LF  AD  AP  ')
         for i, data in enumerate(self.data):
             poll = self.check_normality(data)
             isnormal = any(poll)
@@ -173,7 +187,7 @@ class StatisticalAnalysis(StatisticalTests, NormalityTests, TextFormatting, Help
                 '+' if x is True else '-' if x is False else ' ' if x is None else 'e' for x in poll)
             self.normals.append(isnormal)
             self.log(
-                f'        {self.groups_name[i].ljust(7, ' ')[:7]}:    {poll_print[0]}   {poll_print[1]}   {poll_print[2]}   {poll_print[3]}   so disrtibution seems {"normal" if isnormal else "not normal"}')
+                f'    {self.groups_name[i].ljust(11, ' ')[:11]}:    {poll_print[0]}   {poll_print[1]}   {poll_print[2]}   {poll_print[3]}   so disrtibution seems {"normal" if isnormal else "not normal"}')
         self.parametric = all(self.normals)
 
         # print test choosen